Authenticating a User Subvocalizing a Displayed Text

1. A computing device for authenticating a user of the computing device, the computing device comprising processing circuitry configured to: display a first text to the user, acquire, from one or more sensors operatively connected to the computing device, larynx muscles nerve signals sensed from a throat of the user who is stimulating the larynx muscles while subvocalizing a part of the first text, derive a representation of the user subvocalizing at least the part of the first text as a representation of the larynx muscles nerve signals, derive a user phrasing signature from the derived representation of the larynx muscles nerve signals, authenticate the user in response to determining that the user phrasing signature and a reference phrasing signature fulfil a similarity condition, determine, in response to authenticating the user, if the user is authorized, and display to the user a second text in response to determining that the user is authorized to read the first text and in response to detecting that the user subvocalizes a closing part of the first text.

2. The computing device according to claim 1 , the processing circuitry is further configured to acquire the representation of the user subvocalizing at least a part of the first text by: acquiring, from a camera operatively connected to the computing device, a video sequence of the user subvocalizing the part of the first text, magnifying, by video processing the acquired video sequence, motions of one or more body parts of the user, which motions are correlated with the subvocalized part of the first text, and deriving the representation of the user subvocalizing at least a part of the first text as a representation of the magnified motions.

3. The computing device according to claim 1 , the processing circuitry is further configured to derive the user phrasing signature from the acquired representation by: identifying syllables and pauses in the acquired representation, determining respective durations of the identified syllables and pauses, and deriving the user phrasing signature as a sequence of the determined durations of the syllables and pauses.

4. The computing device according to claim 1 , the processing circuitry is further configured to derive the reference phrasing signature by: identifying syllables and pauses in the first text, acquiring reference durations of syllables and pauses, and deriving the reference phrasing signature as a sequence of the reference durations of the identified syllables and pauses.

5. The computing device according to claim 4 , the processing circuitry is further configured to derive the reference durations of syllables and pauses from acquired representations of the user subvocalizing text by: identifying syllables and pauses in the acquired representations, determining respective durations of the identified syllables and pauses, and storing the determined durations of syllables and pauses as the reference durations of syllables and pauses.

6. The computing device according to claim 4 , wherein the reference durations of syllables and pauses are dependent on a type of text.

7. The computing device according to claim 1 , the processing circuitry is further configured to determine that the user phrasing signature and the reference phrasing signature fulfil a similarity condition by: calculating a correlation between the user phrasing signature and at least a consecutive part of the reference phrasing signature, and determining that the user phrasing signature and the reference phrasing signature fulfil the similarity condition if the calculated correlation exceeds a first threshold value.

8. The computing device according to claim 7 , the processing circuitry is further configured to calculate the correlation between the user phrasing signature and the entire reference phrasing signature, the processing circuitry is further configured to determine that the user has read the first text substantially in its entirety if the calculated correlation exceeds a second threshold value.

9. The computing device according to claim 1 , the processing circuitry is further configured to determine if the user is authorized to read the first text based on permission information associated with the first text.

10. The computing device according to claim 1 , the processing circuitry is further configured to reveal obfuscated parts of the first text in response to determining that the user is authorized to read the first text.

11. The computing device according to claim 1 , the processing circuitry is further configured to discontinue displaying the first text or to obfuscate at least part of the first text in response to determining that the user is not authorized to read the first text.

12. The computing device according to claim 1 , the processing circuitry is further configured to discontinue displaying the first text or to obfuscate at least part of the first text in response to determining that the user phrasing signature and the reference phrasing signature fail to fulfil the similarity condition.

13. The computing device according to claim 1 , being any one of: a mobile phone, a mobile terminal, a smartphone, a tablet, a personal computer, a laptop, an e-book reader, a computer display, a television, and a media player.

14. A method of authenticating a user of a computing device, the method comprising: displaying a first text to the user, acquiring, from one or more sensors operatively connected to the computing device, larynx muscles nerve signals sensed from a throat of the user who is stimulating the larynx muscles while subvocalizing a part of the first text, deriving a representation of the user subvocalizing at least the part of the first text as a representation of the larynx muscles nerve signals, deriving a user phrasing signature from the acquired representation, authenticating the user in response to determining that the user phrasing signature and a reference phrasing signature fulfil a similarity condition, determining, in response to authenticating the user, if the user is authorized, and displaying to the user a second text in response to determining that the user is authorized to read the first text and in response to detecting that the user subvocalizes a closing part of the first text.

15. The method according to claim 14 , wherein the acquiring the representation of the user subvocalizing at least a part of the first text comprises: acquiring, from a camera operatively connected to the computing device, a video sequence of the user subvocalizing the part of the first text, magnifying, by video processing the acquired video sequence, motions of one or more body parts of the user, which motions are correlated with the subvocalized part of the first text, and deriving the representation of the user subvocalizing at least a part of the first text as a representation of the magnified motions.

16. The method according to claim 14 , wherein the deriving the user phrasing signature from the acquired representation comprises: identifying syllables and pauses in the acquired representation, determining respective durations of the identified syllables and pauses, and deriving the user phrasing signature as a sequence of the determined durations of the syllables and pauses.

17. The method according to claim 14 , further comprising deriving the reference phrasing signature by: identifying syllables and pauses in the first text, acquiring reference durations of syllables and pauses, and deriving the reference phrasing signature as a sequence of the reference durations of the identified syllables and pauses.

18. The method according to claim 17 , further comprising deriving the reference durations of syllable and pauses from acquired representations of the user subvocalizing text by: identifying syllables and pauses in the acquired representations, determining respective durations of the identified syllables and pauses, and storing the determined durations of syllables and pauses as the reference durations of syllables and pauses.

19. The method according to claim 17 , wherein the reference durations of syllables and pauses are dependent on a type of text.

20. The method according to claim 14 , wherein the determining that the user phrasing signature and the reference phrasing signature fulfil a similarity condition comprises: calculating a correlation between the user phrasing signature and the reference phrasing signature, and determining that the user phrasing signature and the reference phrasing signature fulfil the similarity condition if the calculated correlation exceeds a threshold value.

21. The method according to claim 20 , wherein the correlation is calculated between the user phrasing signature and the entire reference phrasing signature, the method further comprising determining that the user has read the first text substantially in its entirety if the calculated correlation exceeds a second threshold value.

22. The method according to claim 14 , wherein it is determined that the user is authorized to read the first text based on permission information associated with the first text.

23. The method according to claim 14 , further comprising revealing obfuscated parts of the first text in response to determining that the user is authorized to read the first text.

24. The method according to claim 14 , further comprising discontinuing displaying the first text or obfuscating at least part of the first text in response to determining that the user is not authorized to read the first text.

25. The method according to claim 14 , further comprising discontinuing displaying the first text or obfuscating at least part of the first text in response to determining that the user phrasing signature and the reference phrasing signature fail to fulfil the similarity condition.

26. A computer program product comprising a non-transitory computer-readable storage medium storing computer-executable instructions for causing a device to perform the method according to claim 14 , when the computer-executable instructions are executed on a processing circuitry comprised in the device.

27. The computing device according to claim 1 , wherein the authentication of the user in response to determining that the user phrasing signature and the reference phrasing signature fulfil the similarity condition is further based on determining that no audible vocalization from the larynx was detected while the larynx muscles nerve signals were acquired from the throat of the user who is stimulating the larynx muscles while subvocalizing the part of the first text.

28. The method according to claim 14 , wherein the authenticating the user in response to determining that the user phrasing signature and the reference phrasing signature fulfil the similarity condition is further based on determining that no audible vocalization from the larynx was detected while the larynx muscles nerve signals were acquired from the throat of the user who is stimulating the larynx muscles while subvocalizing the part of the first text.